codebase-spec-extractor

A method for examining an existing codebase and documenting how it works in enough detail to rebuild it without seeing the original source.

In plain words
What is it for?
Use it to prepare implementation-grade specifications for rewrites, onboarding, or vendor handoffs. It is not intended mainly for security audits, performance profiling, or simple README updates.
Why use it?
It makes hidden rules, dependencies, data flows, and implementation decisions explicit for people working on legacy systems or migrations.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/okwinds/miscellany/codebase-spec-extractor
Any agent
npx skills add okwinds/miscellany --skill codebase-spec-extractor
Clone the repo
git clone --depth 1 https://github.com/okwinds/miscellany

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00095 $0.04493
Opus 5 $0.00048 $0.02246
Sonnet 5 $0.00019 $0.00899
Haiku 4.5 $0.00010 $0.00449

Measured 2d ago against content hash 91e2c49dc127, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-spec-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/discover_project.sh, scripts/generate_skeleton.sh, scripts/inventory_elements.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agent/skills/codebase-spec-extractor/SKILL.md · 516 lines

How it starts

The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Spec Extractor

Overview

Extract engineering specifications from existing codebases with one goal: produce documentation so complete that the project can be fully replicated without seeing the original source code.

This is NOT about filling templates. This is about deconstructing every detail and documenting it with engineering precision.

Requirements

  • bash (macOS default Bash 3.2 supported)
  • Standard Unix tools: find, grep, sed, wc, date
  • Optional (recommended): rg (ripgrep) for faster scans in large repos

When to Use

  • You need implementation-grade specs for a codebase (migration, rewrite, onboarding, vendor handoff).
  • You keep finding “implicit rules” in code and want them made explicit.
  • You want a repeatable inventory + spec skeleton + verification workflow.

When NOT to Use

  • You only need a quick architecture overview or a lightweight README update.
  • Your main goal is security auditing, performance profiling, or code style cleanup (use dedicated workflows/tools).
  • The repository contains highly sensitive data and you cannot safely store path-rich reports/specs.

Core Principle: Deconstruction Thinking

The framework is a guide, not a boundary. Real projects are messy, creative, and often surprising. Your job is to:

  1. Discover what exists (not assume what should exist)
  2. Understand why it exists (not just what it does)
  3. Document how to replicate it (not just describe it)

The Deconstruction Questions

For EVERY piece of code, structure, or behavior you encounter, ask:

┌─────────────────────────────────────────────────────────────────┐
│                 The 7 Deconstruction Questions                   │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  1. WHAT is this?                                               │
│     → Name it. Classify it. Place it in context.                │
│                                                                 │
│  2. WHY does it exist?                                          │
│     → What problem does it solve? What would break without it?  │
│                                                                 │
│  3. HOW does it work?                                           │
│     → Step-by-step logic. Every branch. Every edge case.        │
│                                                                 │
│  4. WHAT are its inputs?                                        │
│     → All forms. All sources. All validations.                  │
│                                                                 │
│  5. WHAT are its outputs?                                       │
│     → All forms. All destinations. All side effects.            │
│                                                                 │
│  6. WHAT depends on it? What does it depend on?                 │
│     → Upstream. Downstream. External.                           │
│                                                                 │
│  7. WHAT can go wrong?                                          │
│     → Errors. Failures. Edge cases. Recovery.                   │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 516 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 516 lines · 95 tokens per session scan A 91e2c49dc127

Subscribe to this mod's changes

codebase-spec-extractor is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 4,493 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens